CN115980364A - Application of methylated miR-124 gene in preparation of marker for diagnosing depression - Google Patents
Application of methylated miR-124 gene in preparation of marker for diagnosing depression Download PDFInfo
- Publication number
- CN115980364A CN115980364A CN202310016636.4A CN202310016636A CN115980364A CN 115980364 A CN115980364 A CN 115980364A CN 202310016636 A CN202310016636 A CN 202310016636A CN 115980364 A CN115980364 A CN 115980364A
- Authority
- CN
- China
- Prior art keywords
- depression
- gray matter
- marker
- video
- diagnosing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention belongs to the technical field of depression diagnosis, and discloses application of a methylated miR-124 gene in preparation of a marker for depression diagnosis. According to the method for analyzing the relevant data of the depression patients, the human resources required for the users to obtain the relevant data of the depression by observing the facial changes of the corresponding personnel are reduced according to the depression patient database and the depression database; in addition, the identification efficiency can be greatly improved through the identification of the video, and errors possibly caused by subjective judgment of a user can be reduced; meanwhile, structural magnetic resonance T1 weighted images of brains of a plurality of depression patients are obtained by a predictive analysis method for recurrence of the depression patients; preprocessing a plurality of structural magnetic resonance T1 weighted images to obtain a plurality of gray matter volume maps; constructing a support vector machine classifier based on the size of gray matter volume on a plurality of gray matter volume charts; and (5) predicting the recurrence of the depression according to a support vector machine classifier.
Description
Technical Field
The invention belongs to the technical field of depression diagnosis, and particularly relates to application of a methylated miR-124 gene in preparation of a marker for depression diagnosis.
Background
Depression is now the most common psychological disorder, with continuous and long-term depression as the major clinical feature, the most important type of psychological disorder in modern people. Clinically, the mood is low and the reality is too happy, the mood is low and subsided for a long time, the feeling is from sultriness at the beginning to the final sadness, the people feel alive every day and hopefully afflict themselves, negative, escape and even have suicide tendency and behavior. The patient had somatization symptoms. Chest oppression and shortness of breath. Only want to lie in bed every day, do not want to move. Has obvious anxiety feeling. More serious people will have symptoms of schizophrenia such as auditory hallucinations, delusional disorder and multiple personality. Every episode of depression lasts for at least more than 2 weeks, one year, or even several years, and most cases have a tendency to relapse; however, the use of the existing methylated miR-124 gene in the preparation of markers for diagnosing depression cannot accurately analyze depression data; meanwhile, the prevention of the recurrence of the depression is mainly based on the clinical characteristics of patients and the evaluation of doctors, the subjectivity is strong, the repeatability is poor, and the early-stage recurrence of the depression is difficult to find, so that the accuracy rate of predicting the recurrence of the depression is low.
Through the above analysis, the problems and defects of the prior art are as follows:
(1) The application of the existing methylated miR-124 gene in the preparation of a marker for diagnosing depression cannot accurately analyze depression data.
(2) The prevention of the recurrence of the depression is mainly based on the clinical characteristics of patients and the evaluation of doctors, and has strong subjectivity and poor repeatability, and the early stage of the recurrence of the depression is difficult to discover, so that the accuracy rate of predicting the recurrence of the depression is low.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides an application of a methylated miR-124 gene in preparing a marker for diagnosing depression.
The application of the methylated miR-124 gene in preparing the marker for diagnosing the depression is realized, and the methylated miR-124 gene is any one or the combination of more than two of methylated MIR124-1 gene, MIR124-2 gene or MIR124-3 gene.
Further, the marker for diagnosing depression is an endogenous polypeptide, and the amino acid sequence of the endogenous polypeptide is at least one of SEQ ID NOS.1-14.
Further, the marker for diagnosing depression is a combined marker, and the combined marker is a composition of more than two endogenous polypeptides with at least one sequence of SEQ ID NOS.1-14;
the combination marker is a composition of polypeptides belonging to different proteins;
the combination markers are compositions of polypeptides from different metabolic pathways.
Further, the markers for diagnosing depression, the sequences of which are seq id nos.7, 10 and 11, are up-regulated in the depression group, and the ranges of their contents in the fold-change between the two groups are depression groups: healthy control group =1.01 to 30:1;
the expression of the markers for diagnosing the depression, the sequences of which are SEQIDNos.1-6, SEQIDNos.8-9 and SEQIDNos.12-14, is down-regulated in the depression group, and the content of the markers is within the range of fold change between two groups, namely a healthy control group: depression group =1.01 to 30:1.
further, the endogenous polypeptide is derived from a bodily fluid comprising at least one of plasma, serum, cerebrospinal fluid, or urine.
A method for preparing a marker for diagnosing depression by using a methylated miR-124 gene comprises the following steps:
step one, analyzing relevant data of a depression patient; after analysis, collecting organism liquid samples of depression patients and healthy control volunteers;
step two, preprocessing a biological fluid sample, and obtaining polypeptide maps of the biological fluid of a depression patient and a health control by adopting a nano-upgrading ultra-high performance liquid chromatography-mass spectrometry technology;
step three, screening a group of endogenous polypeptides, taking one of the endogenous polypeptides as a single marker, and observing the up-regulation or down-regulation of the expression in a patient group and a control group; identifying the amino acid sequence of the endogenous polypeptide as SEQIDNos.1-14;
step four, obtaining a receiver operating characteristic ROC curve, an area under the curve AUC, sensitivity and specificity values; and predictive analysis of the recurrence of the depressive disorder;
the sample pretreatment method comprises the steps of protein precipitation by an organic solvent, solid-liquid extraction and liquid-liquid extraction;
the area under the curve AUC value of the receiver operating characteristic ROC curve of the single marker is 0.6-0.999, the sensitivity is 60-99.99%, and the specificity is 60-99.99%.
Further, the preparation method also comprises combining the polypeptides into combined markers in different ways;
the combination includes combining polypeptides belonging to different proteins or combining polypeptides from different metabolic pathways;
the AUC value of the area under the curve of the receiver operating characteristic ROC curve of the combined marker is 0.6-0.999, the sensitivity is 60-99.99%, and the specificity is 60-99.99%.
Further, the markers for diagnosing depression, of which the sequences are seq id nos.7, 10 and 11, are up-regulated in the depression group, and their contents vary in multiples between the two groups within the range of depression group: healthy control group =1.01 to 30:1;
the expression of the markers for diagnosing the depression, the sequences of which are SEQIDNos.1-6, SEQIDNos.8-9 and SEQIDNos.12-14, is down-regulated in the depression group, and the content of the markers is within the range of fold change between two groups, namely a healthy control group: depression group =1.01 to 30:1.
further, the analysis method for the data related to the depression patients is as follows:
(1) Pre-training a first preset deep network model by using a depression patient database to obtain a preliminary network model; training the obtained preliminary network model by using a depression video database to obtain a first recognition model;
(2) Calculating a depression optical flow map set by using the depression video database; training a second preset depth network model by using the depression light flow graph set to obtain a second recognition model; fusing the first recognition model and the second recognition model to obtain a regression model;
(3) Inputting a video to be identified into the regression model to identify the depression patient in the video to be identified so as to obtain depression related data;
the step of calculating the depression optical flow map set by using the depression video database comprises the following steps:
acquiring each frame of image in a depression video database;
calculating a depression light flow graph formed by a horizontal direction, a vertical direction and an amplitude value aiming at each frame of image, and forming the depression light flow atlas according to the depression light flow graph calculated aiming at each frame of image;
the step of inputting the video to be identified into the regression model to identify the depression patients in the video to be identified to obtain depression related data comprises the following steps:
performing depression patient preprocessing on the video to be identified so as to perform depression patient detection on each frame of image in the video to be identified and align detected depression patients;
inputting the preprocessed video to be identified into the regression model to identify the depression patient in the video to be identified so as to obtain the depression related data;
the step of inputting the video to be identified into the regression model to identify the depression patients in the video to be identified to obtain depression related data comprises the following steps:
acquiring each frame of image in the video to be identified;
inputting each frame of image in the video to be identified into the regression model to obtain a depression score corresponding to each frame of image;
calculating according to the depression score corresponding to each frame of image according to a preset calculation rule to obtain a calculation result, and matching the calculation result with a preset depression classification to obtain depression related data;
the step of calculating the depression score corresponding to each frame of image according to a preset calculation rule to obtain a calculation result, and matching the calculation result with a preset depression classification to obtain the depression related data comprises the following steps:
calculating the average value of the depression scores corresponding to each frame of image in the video to be identified;
and calculating the average absolute error or the root mean square error of the average value and the depression score corresponding to each frame of image, and matching the average absolute error or the root mean square error with a preset depression classification to obtain depression related data.
Further, the method for predictive analysis of recurrence of depression patients is as follows:
1) Acquiring structural magnetic resonance T1 weighted images of brains of a plurality of depression patients; preprocessing a plurality of structural magnetic resonance T1 weighted images to obtain a plurality of gray matter volume maps; performing enhancement treatment on the gray matter volume map;
2) Constructing a support vector machine classifier based on the size of gray matter volume on a plurality of gray matter volume charts; predicting the recurrence of the depression according to a classifier of a support vector machine;
the step of preprocessing the plurality of structural magnetic resonance T1 weighted images to obtain a plurality of gray matter volume maps comprises:
converting the multiple structural magnetic resonance T1 weighted image DICOM data into NIFTI format;
dividing a plurality of structural magnetic resonance T1 weighted images in an NIFTI format into three tissue types of gray matter, white matter and cerebrospinal fluid to obtain a plurality of gray matter probability maps;
carrying out normalization processing on a plurality of gray matter probability maps;
registering the multiple gray matter probability maps subjected to normalization processing to an MNI standard space, and modulating the multiple gray matter probability maps by using nonlinear deformation field parameters to obtain multiple initial gray matter volume maps;
performing smoothing filtering processing on the plurality of initial gray matter volume maps to obtain a plurality of gray matter volume maps;
the step of constructing a support vector machine classifier based on the size of gray matter volumes on a plurality of gray matter volume maps comprises:
extracting gray matter volume sizes of 90 independent brain regions from the plurality of gray matter volume maps using an AAL90 template;
constructing a support vector machine classifier by the steps of reserving one cross validation, data normalization processing and searching for the optimal hyper-parameter based on the gray matter volume sizes of 90 independent brain areas on a plurality of gray matter volume maps;
after the step of constructing a support vector machine classifier based on the size of gray matter volumes on the plurality of gray matter volume maps, the method comprises:
evaluating a support vector machine classifier effect using a permutation test;
if the evaluation is passed, executing the step of depression prediction according to a support vector machine classifier;
if the evaluation does not pass, executing a step of constructing a support vector machine classifier based on the size of the gray matter volume on the plurality of gray matter volume maps;
the step of predicting recurrence of depression based on a support vector machine classifier comprises:
and acquiring weight values of the gray matter volume of each brain area in the support vector machine classifier, and evaluating the effect of the gray matter volume of different brain areas in the process of predicting the recurrence of the depression.
In combination with the technical solutions and the technical problems to be solved, please analyze the advantages and positive effects of the technical solutions to be protected in the present invention from the following aspects:
first, aiming at the technical problems existing in the prior art and the difficulty in solving the problems, the technical problems to be solved by the technical scheme of the present invention are closely combined with results, data and the like in the research and development process, and some creative technical effects are brought after the problems are solved. The specific description is as follows:
according to the method, the preset depth network model is trained through the analysis method of the relevant data of the depression patient according to the depression patient database and the depression database, so that depression relevant data corresponding to the features of the depression patient in the video to be identified can be obtained, and the human resources required by the user to obtain the depression relevant data by observing the face changes of the corresponding personnel are reduced; in addition, the identification efficiency can be greatly improved through the identification of the video, and errors possibly caused by subjective judgment of a user can be reduced; meanwhile, structural magnetic resonance T1 weighted images of brains of a plurality of depression patients are obtained by a method for predicting and analyzing relapse of the depression patients; preprocessing a plurality of structural magnetic resonance T1 weighted images to obtain a plurality of gray matter volume maps; constructing a support vector machine classifier based on the size of gray matter volume on a plurality of gray matter volume charts; and (5) predicting the recurrence of the depression according to a support vector machine classifier.
Secondly, considering the technical scheme as a whole or from the perspective of products, the technical effect and advantages of the technical scheme to be protected by the invention are specifically described as follows:
according to the method, the preset depth network model is trained through the analysis method of the relevant data of the depression patient according to the depression patient database and the depression database, so that depression relevant data corresponding to the features of the depression patient in the video to be identified can be obtained, and the human resources required by the user to obtain the depression relevant data by observing the face changes of the corresponding personnel are reduced; in addition, the identification efficiency can be greatly improved through the identification of the video, and errors possibly caused by subjective judgment of a user can be reduced; meanwhile, structural magnetic resonance T1 weighted images of brains of a plurality of depression patients are obtained by a predictive analysis method for recurrence of the depression patients; preprocessing a plurality of structural magnetic resonance T1 weighted images to obtain a plurality of gray matter volume maps; constructing a support vector machine classifier based on the size of gray matter volume on a plurality of gray matter volume charts; and (5) predicting the recurrence of the depression according to a support vector machine classifier.
Drawings
FIG. 1 is a flow chart of the use of a methylated miR-124 gene provided by an embodiment of the invention in the preparation of a marker for diagnosing depression.
Fig. 2 is a flow chart of a method for analyzing data related to a depression patient according to an embodiment of the present invention.
Fig. 3 is a flowchart of a method for predictive analysis of recurrence in a patient with depression according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
1. Illustrative embodiments are explained. This section is an explanatory embodiment expanding on the claims so as to fully understand how the present invention is embodied by those skilled in the art.
The invention provides application of a methylated miR-124 gene in preparation of a marker for diagnosing depression.
The methylated miR-124 gene provided by the invention is any one or the combination of more than two of methylated MIR124-1 gene, MIR124-2 gene or MIR124-3 gene.
The marker for diagnosing depression provided by the invention is an endogenous polypeptide, and the amino acid sequence of the endogenous polypeptide is at least one of SEQ ID NOS.1-14.
The marker for diagnosing the depression provided by the invention is a combined marker, and the combined marker is a composition of more than two endogenous polypeptides with at least one sequence of SEQ ID NOS.1-14;
the combination marker is a composition of polypeptides belonging to different proteins;
the combination markers are compositions of polypeptides from different metabolic pathways.
The sequence provided by the invention is that the markers for diagnosing the depression are expressed up-regulated in a depression group, and the content of the markers for diagnosing the depression is in a range of fold change between two groups, namely the depression group: healthy control group =1.01 to 30:1;
the expression of the markers for diagnosing the depression, the sequences of which are SEQIDNos.1-6, SEQIDNos.8-9 and SEQIDNos.12-14, is down-regulated in the depression group, and the content of the markers is within the range of fold change between two groups, namely a healthy control group: depression group =1.01 to 30:1.
the endogenous polypeptides provided by the invention are derived from a body fluid comprising at least one of plasma, serum, cerebrospinal fluid, or urine.
As shown in figure 1, a method for preparing a marker for diagnosing depression by using a methylated miR-124 gene comprises the following steps:
s101, analyzing relevant data of depression patients; after analysis, collecting organism liquid samples of depression patients and healthy control volunteers;
s102, preprocessing a biological fluid sample, and obtaining polypeptide maps of the biological fluid of a depression patient and a health control by adopting a nano-upgrading ultra-high performance liquid chromatography-mass spectrometry technology;
s103, screening a group of endogenous polypeptides, taking one of the endogenous polypeptides as a single marker, and observing the up-regulation or down-regulation of the expression in a patient group and a control group; identifying the amino acid sequence of the endogenous polypeptide as SEQIDNos.1-14;
s104, obtaining a receiver operating characteristic ROC curve, an area AUC under the curve, sensitivity and specificity values; and predictive analysis of recurrence in patients with depression;
according to the method, the preset depth network model is trained through the analysis method of the relevant data of the depression patient according to the depression patient database and the depression database, so that depression relevant data corresponding to the features of the depression patient in the video to be identified can be obtained, and the human resources required by the user to obtain the depression relevant data by observing the face changes of the corresponding personnel are reduced; in addition, the identification efficiency can be greatly improved through the identification of the video, and errors possibly caused by subjective judgment of a user can be reduced; meanwhile, structural magnetic resonance T1 weighted images of brains of a plurality of depression patients are obtained by a predictive analysis method for recurrence of the depression patients; preprocessing a plurality of structural magnetic resonance T1 weighted images to obtain a plurality of gray matter volume maps; constructing a support vector machine classifier based on the size of gray matter volume on a plurality of gray matter volume charts; and (5) predicting the recurrence of the depression according to a support vector machine classifier.
The sample pretreatment method comprises the steps of protein precipitation by an organic solvent, solid-liquid extraction and liquid-liquid extraction;
the area under the curve AUC value of the receiver operating characteristic ROC curve of the single marker is 0.6-0.999, the sensitivity is 60-99.99%, and the specificity is 60-99.99%.
The preparation method provided by the invention also comprises the steps of combining the polypeptides into combined markers in different ways;
the combination includes combining polypeptides belonging to different proteins or combining polypeptides from different metabolic pathways;
the AUC value of the area under the curve of the receiver operating characteristic ROC curve of the combined marker is 0.6-0.999, the sensitivity is 60-99.99%, and the specificity is 60-99.99%.
The sequence provided by the invention is that the markers for diagnosing the depression are expressed up-regulated in a depression group, and the content of the markers for diagnosing the depression is in a range of fold change between two groups, namely the depression group: healthy control group =1.01 to 30:1;
the expression of the markers for diagnosing the depression, the sequences of which are SEQIDNos.1-6, SEQIDNos.8-9 and SEQIDNos.12-14, is down-regulated in the depression group, and the content of the markers is within the range of fold change between two groups, namely a healthy control group: depression group =1.01 to 30:1.
as shown in fig. 2, the present invention provides the following method for analyzing data related to depression patients:
s201, pre-training a first preset deep network model by using a depression patient database to obtain a preliminary network model; training the obtained preliminary network model by using a depression video database to obtain a first recognition model;
s202, calculating to obtain a depression optical flow atlas by using the depression video database; training a second preset depth network model by using the depression light flow graph set to obtain a second recognition model; fusing the first recognition model and the second recognition model to obtain a regression model;
s203, inputting the video to be identified into the regression model to identify the depression patient in the video to be identified, and obtaining depression related data;
according to the method, the preset depth network model is trained through the analysis method of the relevant data of the depression patient according to the depression patient database and the depression database, so that depression relevant data corresponding to the features of the depression patient in the video to be identified can be obtained, and the human resources required by the user to obtain the depression relevant data by observing the face changes of the corresponding personnel are reduced; in addition, the efficiency of identification can be greatly improved through the identification of the video, and errors possibly generated by subjective judgment of a user can also be reduced.
The step of using the depression video database to calculate a depression optical flow atlas comprises:
acquiring each frame of image in a depression video database;
calculating a depression light flow graph formed by a horizontal direction, a vertical direction and an amplitude value aiming at each frame of image, and forming the depression light flow atlas according to the depression light flow graph calculated aiming at each frame of image;
the step of inputting the video to be identified into the regression model to identify the depression patients in the video to be identified to obtain depression related data comprises the following steps:
performing depression patient preprocessing on the video to be identified so as to perform depression patient detection on each frame of image in the video to be identified and align detected depression patients;
inputting the preprocessed video to be identified into the regression model to identify the depression patient in the video to be identified so as to obtain the depression related data;
the step of inputting the video to be identified into the regression model to identify the depression patients in the video to be identified to obtain depression related data comprises the following steps:
acquiring each frame of image in the video to be identified;
inputting each frame of image in the video to be identified into the regression model to obtain a depression score corresponding to each frame of image;
calculating according to the depression score corresponding to each frame of image according to a preset calculation rule to obtain a calculation result, and matching the calculation result with a preset depression classification to obtain depression related data;
the step of calculating the depression score corresponding to each frame of image according to a preset calculation rule to obtain a calculation result, and matching the calculation result with a preset depression classification to obtain the depression related data comprises the following steps:
calculating the average value of the depression scores corresponding to each frame of image in the video to be identified;
and calculating the average absolute error or the root mean square error of the average value and the depression score corresponding to each frame of image, and matching the average absolute error or the root mean square error with a preset depression classification to obtain the depression related data.
As shown in fig. 3, the method for predicting and analyzing recurrence of depression patients provided by the present invention comprises the following steps:
s301, acquiring structural magnetic resonance T1 weighted images of brains of a plurality of depression patients; preprocessing a plurality of structural magnetic resonance T1 weighted images to obtain a plurality of gray matter volume maps; performing enhancement treatment on the gray matter volume map;
s302, constructing a support vector machine classifier based on the size of the gray matter volume on the gray matter volume maps; predicting the recurrence of the depression according to a support vector machine classifier;
the invention obtains structural magnetic resonance T1 weighted images of brains of a plurality of depression patients by a predictive analysis method for the recurrence of the depression patients; preprocessing a plurality of structural magnetic resonance T1 weighted images to obtain a plurality of gray matter volume maps; constructing a support vector machine classifier based on the size of gray matter volume on a plurality of gray matter volume charts; and (5) predicting the recurrence of the depression according to a support vector machine classifier.
The step of preprocessing the plurality of structural magnetic resonance T1 weighted images to obtain a plurality of gray matter volume maps comprises:
converting the multiple structural magnetic resonance T1 weighted image DICOM data into NIFTI format;
dividing a plurality of structural magnetic resonance T1 weighted images in an NIFTI format into three tissue categories of gray matter, white matter and cerebrospinal fluid to obtain a plurality of gray matter probability maps;
carrying out normalization processing on a plurality of gray matter probability maps;
registering the multiple gray matter probability maps subjected to normalization processing to an MNI standard space, and modulating the multiple gray matter probability maps by using nonlinear deformation field parameters to obtain multiple initial gray matter volume maps;
performing smoothing filtering processing on the plurality of initial gray matter volume maps to obtain a plurality of gray matter volume maps;
the step of constructing a support vector machine classifier based on the size of gray matter volumes on a plurality of gray matter volume maps comprises:
extracting gray matter volume sizes of 90 independent brain regions from the plurality of gray matter volume maps using an AAL90 template;
constructing a support vector machine classifier by the steps of reserving one cross validation, data normalization processing and searching for the optimal hyper-parameter based on the gray matter volume sizes of 90 independent brain areas on a plurality of gray matter volume maps;
after the step of constructing a support vector machine classifier based on the size of gray matter volumes on the plurality of gray matter volume maps, the method comprises:
evaluating a support vector machine classifier effect using a permutation test;
if the evaluation is passed, executing the step of depression prediction according to a support vector machine classifier;
if the evaluation does not pass, executing a step of constructing a support vector machine classifier based on the size of the gray matter volume on the plurality of gray matter volume maps;
the step of predicting recurrence of depression based on a support vector machine classifier comprises:
and acquiring weight values of the gray matter volume of each brain area in the support vector machine classifier, and evaluating the effect of the gray matter volume of different brain areas in the process of predicting the recurrence of the depression.
2. Application examples. In order to prove the creativity and the technical value of the technical scheme of the invention, the part is the application example of the technical scheme of the claims on specific products or related technologies.
According to the method, the preset depth network model is trained through the analysis method of the relevant data of the depression patient according to the depression patient database and the depression database, so that depression relevant data corresponding to the features of the depression patient in the video to be identified can be obtained, and the human resources required by the user to obtain the depression relevant data by observing the face changes of the corresponding personnel are reduced; in addition, the identification efficiency can be greatly improved through the identification of the video, and errors possibly caused by subjective judgment of a user can be reduced; meanwhile, structural magnetic resonance T1 weighted images of brains of a plurality of depression patients are obtained by a predictive analysis method for recurrence of the depression patients; preprocessing a plurality of structural magnetic resonance T1 weighted images to obtain a plurality of gray matter volume maps; constructing a support vector machine classifier based on the size of gray matter volume on a plurality of gray matter volume charts; and (5) predicting the recurrence of the depression according to a support vector machine classifier.
It should be noted that the embodiments of the present invention can be realized by hardware, software, or a combination of software and hardware. The hardware portion may be implemented using dedicated logic; the software portions may be stored in a memory and executed by a suitable instruction execution system, such as a microprocessor or specially designed hardware. Those skilled in the art will appreciate that the apparatus and methods described above may be implemented using computer executable instructions and/or embodied in processor control code, such code being provided on a carrier medium such as a disk, CD-or DVD-ROM, programmable memory such as read only memory (firmware), or a data carrier such as an optical or electronic signal carrier, for example. The apparatus and its modules of the present invention may be implemented by hardware circuits such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., or by software executed by various types of processors, or by a combination of hardware circuits and software, e.g., firmware.
3. Evidence of the relevant effects of the examples. The embodiment of the invention achieves some positive effects in the process of research and development or use, and has great advantages compared with the prior art, and the following contents are described by combining data, diagrams and the like in the test process.
According to the method, the preset depth network model is trained through the analysis method of the relevant data of the depression patient according to the depression patient database and the depression database, so that depression relevant data corresponding to the features of the depression patient in the video to be identified can be obtained, and the human resources required by the user to obtain the depression relevant data by observing the face changes of the corresponding personnel are reduced; in addition, the identification efficiency can be greatly improved through the identification of the video, and errors possibly caused by subjective judgment of a user can be reduced; meanwhile, structural magnetic resonance T1 weighted images of brains of a plurality of depression patients are obtained by a predictive analysis method for recurrence of the depression patients; preprocessing a plurality of structural magnetic resonance T1 weighted images to obtain a plurality of gray matter volume maps; constructing a support vector machine classifier based on the size of the gray matter volume on a plurality of gray matter volume maps; and (5) predicting the recurrence of the depression according to a support vector machine classifier.
The above description is only for the purpose of illustrating the embodiments of the present invention, and the scope of the present invention should not be limited thereto, and any modifications, equivalents and improvements made by those skilled in the art within the technical scope of the present invention as disclosed in the present invention should be covered by the scope of the present invention.
Claims (10)
1. Use of a methylated miR-124 gene in preparation of a marker for diagnosing depression, wherein the methylated miR-124 gene is any one or a combination of more than two of methylated MIR124-1 gene, MIR124-2 gene or MIR124-3 gene.
2. The use of the methylated miR-124 gene in the preparation of a marker for diagnosing depression according to claim 1, wherein the marker for diagnosing depression is an endogenous polypeptide, and the amino acid sequence of the endogenous polypeptide is at least one of SEQ ID NOS.1-14.
3. The use of the methylated miR-124 gene of claim 2 for the preparation of a marker for diagnosing depression, wherein the marker for diagnosing depression is a combination marker, the combination marker is a combination of two or more endogenous polypeptides having at least one of seq id nos.1-14;
the combination marker is a composition of polypeptides belonging to different proteins;
the combination markers are compositions of polypeptides from different metabolic pathways.
4. The use of the methylated miR-124 gene in the preparation of a marker for diagnosing depression according to claim 2, wherein the markers for diagnosing depression, the sequences of which are SEQ ID NO. 7, SEQ ID NO. 10 and SEQ ID NO. 11, are up-regulated in the depression group, and the content of which varies by multiples between the two groups is in the range of the depression group: healthy control group =1.01 to 30:1;
the expression of the markers for diagnosing depression with the sequence of SEQ ID NOS.1-6, 8-9 and 12-14 is reduced in depression group, and the range of the fold change of the contents of the markers between the two groups is that of a healthy control group: depression group = 1.01-30: 1.
5. use of the methylated miR-124 gene of claim 2 in the preparation of a marker for diagnosing depression, wherein the endogenous polypeptide is derived from a body fluid comprising at least one of plasma, serum, cerebrospinal fluid or urine.
6. The method for preparing the marker for diagnosing the depression by using the methylated miR-124 gene as claimed in claim 1, wherein the method for preparing the marker for diagnosing the depression by using the methylated miR-124 gene comprises the following steps of:
step one, analyzing relevant data of a depression patient; after analysis, collecting organism liquid samples of depression patients and healthy control volunteers;
step two, preprocessing a biological fluid sample, and obtaining polypeptide maps of the biological fluid of a depression patient and a health control by adopting a nano-upgrading ultra-high performance liquid chromatography-mass spectrometry technology;
step three, screening a group of endogenous polypeptides, taking one of the endogenous polypeptides as a single marker, and observing the up-regulation or down-regulation of the expression in a patient group and a control group; identifying the amino acid sequence of the endogenous polypeptide as SEQIDNos.1-14;
step four, obtaining a receiver operating characteristic ROC curve, an area under the curve AUC, sensitivity and specificity values; and predictive analysis of the recurrence of the depressive disorder;
the sample pretreatment method comprises the steps of protein precipitation by an organic solvent, solid-liquid extraction and liquid-liquid extraction;
the area under the curve AUC value of the receiver operating characteristic ROC curve of the single marker is 0.6-0.999, the sensitivity is 60-99.99%, and the specificity is 60-99.99%.
7. The method for preparing a marker for diagnosing depression according to claim 6, wherein the preparation method further comprises differently combining the polypeptides into a combined marker;
the combination includes combining polypeptides belonging to different proteins or combining polypeptides from different metabolic pathways;
the AUC value of the area under the curve of the receiver operating characteristic ROC curve of the combined marker is 0.6-0.999, the sensitivity is 60-99.99%, and the specificity is 60-99.99%.
8. The method for preparing the marker for diagnosing the depression according to claim 6, wherein the markers for diagnosing the depression, the sequences of which are SEQ ID NO. 7, SEQ ID NO. 10 and SEQ ID NO. 11, are up-regulated in the depression group, and the content of the markers for diagnosing the depression varies in a multiple manner between the two groups is in the depression group: healthy control group =1.01 to 30:1;
the expression of the markers for diagnosing depression with the sequence of SEQ ID NOS.1-6, 8-9 and 12-14 is reduced in depression group, and the range of the fold change of the contents of the markers between the two groups is that of a healthy control group: depression group =1.01 to 30:1.
9. the method for preparing a marker for diagnosing depression according to claim 6, wherein the data related to depression patients are analyzed as follows:
(1) Pre-training a first preset deep network model by using a depression patient database to obtain a preliminary network model; training the obtained preliminary network model by using a depression video database to obtain a first recognition model;
(2) Calculating a depression optical flow map set by using the depression video database; training a second preset depth network model by using the depression light flow graph set to obtain a second recognition model; fusing the first recognition model and the second recognition model to obtain a regression model;
(3) Inputting a video to be identified into the regression model to identify the depression patient in the video to be identified so as to obtain depression related data;
the step of using the depression video database to calculate a depression optical flow atlas comprises:
acquiring each frame of image in a depression video database;
calculating a depression light flow graph formed by a horizontal direction, a vertical direction and an amplitude value aiming at each frame of image, and forming the depression light flow atlas according to the depression light flow graph calculated aiming at each frame of image;
the step of inputting the video to be identified into the regression model to identify the depression patients in the video to be identified to obtain depression related data comprises the following steps:
performing depression patient preprocessing on the video to be identified so as to perform depression patient detection on each frame of image in the video to be identified and align detected depression patients;
inputting the preprocessed video to be identified into the regression model to identify the depression patient in the video to be identified so as to obtain the depression related data;
the step of inputting the video to be identified into the regression model to identify the depression patients in the video to be identified to obtain depression related data comprises the following steps:
acquiring each frame of image in the video to be identified;
inputting each frame of image in the video to be identified into the regression model to obtain a depression score corresponding to each frame of image;
calculating according to the depression score corresponding to each frame of image according to a preset calculation rule to obtain a calculation result, and matching the calculation result with a preset depression classification to obtain depression related data;
the step of calculating the depression score corresponding to each frame of image according to a preset calculation rule to obtain a calculation result, and matching the calculation result with a preset depression classification to obtain the depression related data comprises the following steps:
calculating the average value of the depression scores corresponding to each frame of image in the video to be identified;
and calculating the average absolute error or the root mean square error of the average value and the depression score corresponding to each frame of image, and matching the average absolute error or the root mean square error with a preset depression classification to obtain depression related data.
10. The method for preparing a marker for diagnosing the depression by using the methylated miR-124 gene of claim 6, wherein the method for carrying out predictive analysis on the relapse of the depression patient is as follows:
1) Acquiring structural magnetic resonance T1 weighted images of brains of a plurality of depression patients; preprocessing a plurality of structural magnetic resonance T1 weighted images to obtain a plurality of gray matter volume maps; performing enhancement treatment on the gray matter volume map;
2) Constructing a support vector machine classifier based on the size of gray matter volume on a plurality of gray matter volume charts; predicting the recurrence of the depression according to a support vector machine classifier;
the step of preprocessing the plurality of structural magnetic resonance T1 weighted images to obtain a plurality of gray matter volume maps comprises:
converting the multiple structural magnetic resonance T1 weighted image DICOM data into NIFTI format;
dividing a plurality of structural magnetic resonance T1 weighted images in an NIFTI format into three tissue categories of gray matter, white matter and cerebrospinal fluid to obtain a plurality of gray matter probability maps;
carrying out normalization processing on a plurality of gray matter probability maps;
registering the multiple gray matter probability maps subjected to normalization processing to an MNI standard space, and modulating the multiple gray matter probability maps by using nonlinear deformation field parameters to obtain multiple initial gray matter volume maps;
performing smoothing filtering processing on the plurality of initial gray matter volume maps to obtain a plurality of gray matter volume maps;
the step of constructing a support vector machine classifier based on the size of gray matter volumes on a plurality of gray matter volume maps comprises:
extracting gray matter volume sizes of 90 independent brain regions from a plurality of gray matter volume maps using an AAL90 template;
constructing a support vector machine classifier by the steps of reserving one cross validation, data normalization processing and searching for the optimal hyper-parameter based on the gray matter volume sizes of 90 independent brain areas on a plurality of gray matter volume maps;
after the step of constructing a support vector machine classifier based on the size of gray matter volumes on the plurality of gray matter volume maps, the method comprises:
evaluating a support vector machine classifier effect using a permutation test;
if the evaluation is passed, executing the step of depression prediction according to a support vector machine classifier;
if the evaluation does not pass, executing a step of constructing a support vector machine classifier based on the size of the gray matter volume on the plurality of gray matter volume maps;
the step of predicting recurrence of depression based on a support vector machine classifier comprises:
and obtaining weight values of gray matter volume sizes of all brain areas in the support vector machine classifier, and evaluating the effect of the gray matter volume sizes of different brain areas in the depression recurrence prediction process.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310016636.4A CN115980364A (en) | 2023-01-06 | 2023-01-06 | Application of methylated miR-124 gene in preparation of marker for diagnosing depression |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310016636.4A CN115980364A (en) | 2023-01-06 | 2023-01-06 | Application of methylated miR-124 gene in preparation of marker for diagnosing depression |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115980364A true CN115980364A (en) | 2023-04-18 |
Family
ID=85973934
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310016636.4A Pending CN115980364A (en) | 2023-01-06 | 2023-01-06 | Application of methylated miR-124 gene in preparation of marker for diagnosing depression |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115980364A (en) |
-
2023
- 2023-01-06 CN CN202310016636.4A patent/CN115980364A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110840468B (en) | Autism risk assessment method and device, terminal device and storage medium | |
| CN108109140A (en) | Low Grade Gliomas citric dehydrogenase non-destructive prediction method and system based on deep learning | |
| CN110890137A (en) | Modeling method, device and application of compound toxicity prediction model | |
| US9940383B2 (en) | Method, an arrangement and a computer program product for analysing a biological or medical sample | |
| US11972870B2 (en) | Systems and methods for predicting patient outcome to cancer therapy | |
| Xu et al. | Using transfer learning on whole slide images to predict tumor mutational burden in bladder cancer patients | |
| CN114999629A (en) | AD early prediction method, system and device based on multi-feature fusion | |
| CN110991536A (en) | Training method of early warning model of primary liver cancer | |
| CN114600155A (en) | Weakly supervised multitask learning for cell detection and segmentation | |
| CN107463797B (en) | Biological information analysis method and device for high-throughput sequencing, equipment and storage medium | |
| KR101067352B1 (en) | System and method comprising algorithm for mode-of-action of microarray experimental data, experiment/treatment condition-specific network generation and experiment/treatment condition relation interpretation using biological network analysis, and recording media having program therefor | |
| Ong et al. | Detection of subtle white matter lesions in MRI through texture feature extraction and boundary delineation using an embedded clustering strategy | |
| Wei et al. | Multi-scale sequential feature selection for disease classification using Raman spectroscopy data | |
| US20070072250A1 (en) | Method and system for analysis of cancer biomarkers using proteome image mining | |
| CN115980364A (en) | Application of methylated miR-124 gene in preparation of marker for diagnosing depression | |
| CN116312800A (en) | Lung cancer characteristic identification method, device and storage medium based on circulating RNA whole transcriptome sequencing in blood plasma | |
| Huang et al. | Using fuzzy systems to infer memory impairment from MRI | |
| US20180181705A1 (en) | Method, an arrangement and a computer program product for analysing a biological or medical sample | |
| CN115128285A (en) | Kit and system for identifying and evaluating thyroid follicular tumor by protein combination | |
| WO2016121715A1 (en) | Method for providing information for evaluating prognosis of lung cancer patient, method for predicting prognosis of lung cancer patient, internal standard, antibody, device for predicting prognosis of lung cancer patient, program for prognosis prediction device, and recording medium | |
| CN113990485A (en) | Method for diagnosing diseases based on conventional test data and knowledge graph | |
| Rong et al. | Image-based quantification of histological features as a function of spatial location using the Tissue Positioning System | |
| Khene et al. | Clinical application of digital and computational pathology in renal cell carcinoma: a systematic review | |
| EP4195219A1 (en) | Means and methods for the binary classification of ms1 maps and the recognition of discriminative features in proteomes | |
| Kalkan et al. | Prediction of Alzheimer’s Disease by a Novel Image-Based Representation of Gene Expression. Genes 2022, 13, 1406 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |